Related papers: Dynamic Shielding for Reinforcement Learning in Bl…
Reinforcement learning (RL) has been successfully applied to a variety of robotics applications, where it outperforms classical methods. However, the safety aspect of RL and the transfer to the real world remain an open challenge. A…
Safe exploration is a common problem in reinforcement learning (RL) that aims to prevent agents from making disastrous decisions while exploring their environment. A family of approaches to this problem assume domain knowledge in the form…
Deep reinforcement learning (RL) has shown promising results in the motion planning of manipulators. However, no method guarantees the safety of highly dynamic obstacles, such as humans, in RL-based manipulator control. This lack of formal…
Designing Reinforcement Learning (RL) solutions for real-life problems remains a significant challenge. A major area of concern is safety. "Shielding" is a popular technique to enforce safety in RL by turning user-defined safety…
Empowering safe exploration of reinforcement learning (RL) agents during training is a critical challenge towards their deployment in many real-world scenarios. When prior knowledge of the domain or task is unavailable, training RL agents…
This paper targets the efficient construction of a safety shield for decision making in scenarios that incorporate uncertainty. Markov decision processes (MDPs) are prominent models to capture such planning problems. Reinforcement learning…
While Deep Reinforcement Learning (DRL) has achieved remarkable success across various domains, it remains vulnerable to occasional catastrophic failures without additional safeguards. An effective solution to prevent these failures is to…
The growing trend of fledgling reinforcement learning systems making their way into real-world applications has been accompanied by growing concerns for their safety and robustness. In recent years, a variety of approaches have been put…
Obtaining safety guarantees for reinforcement learning is a major challenge to achieve applicability for real-world tasks. Safety shields extend standard reinforcement learning and achieve hard safety guarantees. However, existing safety…
Safety is still one of the major research challenges in reinforcement learning (RL). In this paper, we address the problem of how to avoid safety violations of RL agents during exploration in probabilistic and partially unknown…
Shielding is a common method used to guarantee the safety of a system under a black-box controller, such as a neural network controller from deep reinforcement learning (DRL), with simpler, verified controllers. Existing shielding methods…
Development of autonomous cyber system defense strategies and action recommendations in the real-world is challenging, and includes characterizing system state uncertainties and attack-defense dynamics. We propose a data-driven deep…
Reinforcement learning algorithms discover policies that maximize reward, but do not necessarily guarantee safety during learning or execution phases. We introduce a new approach to learn optimal policies while enforcing properties…
In real-life scenarios, a Reinforcement Learning (RL) agent aiming to maximise their reward, must often also behave in a safe manner, including at training time. Thus, much attention in recent years has been given to Safe RL, where an agent…
Multi-Agent Reinforcement Learning (MARL) discovers policies that maximize reward but do not have safety guarantees during the learning and deployment phases. Although shielding with Linear Temporal Logic (LTL) is a promising formal method…
Reinforcement learning (RL) is a powerful framework for optimal decision-making and control but often lacks provable guarantees for safety-critical applications. In this paper, we introduce a novel recovery-based shielding framework that…
Reinforcement Learning (RL) has been shown to be effective in many scenarios. However, it typically requires the exploration of a sufficiently large number of state-action pairs, some of which may be unsafe. Consequently, its application to…
Safety remains an open problem in reinforcement learning (RL), especially during training. While safety filters are promising to address safe exploration, they are generally poorly suited for high-dimensional systems with unknown dynamics.…
In recent years, Deep Reinforcement Learning (DRL) has emerged as an effective approach to solving real-world tasks. However, despite their successes, DRL-based policies suffer from poor reliability, which limits their deployment in…
This paper presents a secure reinforcement learning (RL) based control method for unknown linear time-invariant cyber-physical systems (CPSs) that are subjected to compositional attacks such as eavesdropping and covert attack. We consider…